MosaicLeaks: Can your research agent keep a secret?
• 14
AI & ML interests
None defined yet.
Recent Activity
Papers
Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning
CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
Articles
rajeswarsai
authored a
paper 1 day ago
amitsaha
authored a
paper 2 days ago
rajeswarsai
authored 5
papers 2 days ago
Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning
Paper • 2605.09364 • Published
Therefore I am. I Think
Paper • 2604.01202 • Published • 33
VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing
Paper • 2603.29852 • Published • 6
ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
Paper • 2511.00903 • Published
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
Paper • 2508.09804 • Published
amitsaha
submitted a
paper to Daily Papers 7 days ago
xhluca
authored a
paper 13 days ago
fannyrancourt
published a
dataset 21 days ago
aldro61
updated a
dataset 22 days ago
HYTYH
updated a
dataset 22 days ago
spandanagella
authored 4
papers 25 days ago
VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing
Paper • 2603.29852 • Published • 6
Mem-$π$: Adaptive Memory through Learning When and What to Generate
Paper • 2605.21463 • Published • 9
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
Paper • 2606.21638 • Published • 8
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
Paper • 2606.21710 • Published • 4
manveertamber
submitted a
paper to Daily Papers 27 days ago
manveertamber
authored 3
papers 27 days ago
FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs
Paper • 2410.13210 • Published
Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
Paper • 2505.19274 • Published
Unifying Adversarial Robustness and Training Across Text Scoring Models
Paper • 2602.00857 • Published